Comprehensive reference for administering OpenClaw via CLI. Covers channels, agents, models, config, gateway, security, and maintenance.
openclaw.json directly. Use openclaw config set/get/unset or dedicated subcommands.openclaw gateway restartagent field inside account config. Route via bindings array instead.streaming: must be string "off", not boolean false.config set need --strict-json.openclaw status or the relevant status command.openclaw status # overview
openclaw status --deep # detailed
openclaw doctor # find problems
openclaw doctor --fix # auto-fix what it can
openclaw gateway health # gateway health check
openclaw security audit # security scan
openclaw security audit --deep --fix # deep scan + auto-fix
Load the docs before turning it loose — the difference is night and day.
cd ~/.openclaw
claude
# "Read https://docs.openclaw.ai/cli — the full CLI reference.
# Now read the config and architecture pages too."
# Then: "Audit this workspace for security issues."
For the full CLI cheatsheet covering all commands, config paths, and examples:
→ Read references/cli-cheatsheet.md
For security findings, applied fixes, and remaining remediation items:
→ Read references/security-audit.md
| Mistake | Fix |
|---|---|
| --------- | ----- |
Put agent field in Telegram account config | Use bindings array at top level |
Set streaming: false (boolean) | Must be streaming: "off" (string) |
| Edited openclaw.json directly | Use CLI commands; openclaw config set |
| Forgot gateway restart after config | Always openclaw gateway restart |
Used jared@ for VPS SSH | Must use root@clawdbot |
Set dmPolicy: "open" with allowFrom: ["*"] | Use "pairing" or explicit user IDs |
Set controlUi.allowedOrigins: ["*"] | Restrict to ["http://localhost:PORT"] |
共 1 个版本